训练反而让神经网络与大脑视觉皮层的匹配度下降，挑战了学习能更好模拟大脑的假设。
Supervised Training Rapidly Degrades Early Visual Cortex Alignment Across Biologically Plausible Learning Rules
- 对比四种学习规则，仅训练一回合就使初级视觉皮层对齐度下降25%-90%
- 反向传播导致对齐度下降最严重（相关系数下降0.080），而预测编码等规则保留更多
- 未训练的随机网络有时比训练过的网络更接近大脑反应模式
未经训练的随机神经网络在表征相似性上往往与人类大脑早期视觉皮层一致甚至更优，这一现象挑战了‘学习能提升脑机对齐’的普遍假设。研究通过跟踪四种生物合理学习规则（反向传播、反馈对齐、预测编码、尖峰时序可塑性）在训练过程中的表征相似性分析（RSA）对齐情况，使用来自THINGS数据库的720张物体图像及三位受试者六个视觉区域的fMRI数据，在八个训练阶段（第0-40轮）测量模型与大脑表示差异矩阵间的斯皮尔曼相关系数。结果发现：(1) 仅一个训练周期即导致初级视皮层（V1）对齐度下降25%-90%，具体取决于学习规则；(2) 反向传播对齐度下降最显著（Δr = -0.080），而预测编码和STDP保留较多对齐能力（Δr ≈ -0.04）；(3) 在物体选择性皮层（LOC）中出现相反趋势，反向传播在训练中对齐度上升最多，但绝对变化较小。
原文摘要 · Abstract (English)
CORRECTION (August 2026): the central finding of this paper is not supported. An evaluation-mode defect left the batch-normalisation layers of the predictive-coding and STDP conditions in training mode during feature extraction, producing their apparent preservation of V1 alignment. With the defect repaired, predictive coding degrades V1 alignment more than backpropagation does, not less. The finding that training degrades V1 alignment for every rule tested does survive. See the correction note on page 1; the original abstract below and the body are unchanged from v1. Corrected analysis: arXiv:2608.12408. Random, untrained neural networks consistently match or exceed trained networks in representational similarity to early visual cortex. This puzzling finding challenges the assumption that learning improves brain alignment. We investigate it by tracking representational similarity analysis (RSA) alignment to human fMRI data across training for four learning rules: backpropagation (BP), feedback alignment (FA), predictive coding (PC), and spike-timing-dependent plasticity (STDP). Using 720 object images from the THINGS database and fMRI data from three subjects across six visual ROIs, we measure Spearman correlations between model and brain representational dissimilarity matrices at eight training checkpoints (epochs 0-40). We find that (1) a single epoch of training reduces V1 alignment by 25-90%, depending on the learning rule; (2) backpropagation reduces V1 alignment most severely (delta r = -0.080), while predictive coding and STDP preserve substantially more (delta r ~ -0.04); and (3) a weaker, opposite tendency appears in object-selective cortex (LOC), where BP shows the largest increase in alignment during training, although the absolute change is small.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。